AI Security Engineer
LLM Red Teaming • ML Security
Securing AI systems through red teaming, adversarial testing, and vulnerability research. Specializing in LLM security, prompt injection defense, and ML system hardening.
Seattle, WA · Open to AI Security & Red Team roles.
Security Stack & Skills
Security Research & Projects
View all →BlackHalo↗
AI-powered security platform for automated vulnerability discovery, threat intelligence, and security operations.
AI Security & LLM Red Teaming(ACTIVE)
Security-focused research and tooling for prompt injection attacks, jailbreak discovery, adversarial ML, and AI system hardening.
Secure LLM Fine-Tuning
Fine-tuned LLMs with safety guardrails using LoRA adapters, including security-focused evaluations and alignment testing.
Secure RAG Pipeline
Built a retrieval-augmented generation system with input sanitization, access controls, and prompt injection defenses.
Transformer Security Analysis
Deep-dive into transformer internals to understand attack surfaces, embedding vulnerabilities, and defense mechanisms.